Add new SentenceTransformer model.

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,816 @@
+---
+base_model: BAAI/bge-m3
+datasets: []
+language:
+- es
+library_name: sentence-transformers
+license: apache-2.0
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@3
+- cosine_accuracy@5
+- cosine_accuracy@10
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@10
+- cosine_mrr@10
+- cosine_map@100
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:81
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: Disposeu del servei OAC360º d'assistència en la tramitació electrònica
+    amb el que podeu contactar de dilluns a divendres de 08:00 a 20:00 a través del
+    tel. 935 955 094, del correu oac360@sitges.cat, o del servei Truca'm, omplint
+    el formulari perquè us truquin.
+  sentences:
+  - Com es pot demanar la comunicació prèvia d'obres per instal·lacions de plaques
+    solars en sol urbà?
+  - Quin és el correu electrònic per contactar amb el servei OAC360º?
+  - Quin és l'efecte del silenci administratiu?
+- source_sentence: Positiu, llevat els casos en els quals manquin informes preceptius
+    i vinculants d’altres administracions o d’aquells en els què es transfereixin
+    al sol·licitant facultats contràries al planejament i la legislació urbanística.
+  sentences:
+  - Quin és el document que cal aportar per a aquest tràmit?
+  - Quin és el lloc on es pot tramitar la presentació de justificants de pagament
+    per als ajuts del lloguer just dels habitatges?
+  - Quin és el sentit del silenci administratiu per a la comunicació prèvia d'obres
+    per instal·lacions de plaques solars en sol urbà?
+model-index:
+- name: BGE large Legal Spanish
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 1024
+      type: dim_1024
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.1111111111111111
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.3333333333333333
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.4444444444444444
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.7777777777777778
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.1111111111111111
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.1111111111111111
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.08888888888888889
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.07777777777777778
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.1111111111111111
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.3333333333333333
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.4444444444444444
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.7777777777777778
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.37561164042849293
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.2550705467372134
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.26453109424123916
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.1111111111111111
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.3333333333333333
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.4444444444444444
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.7777777777777778
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.1111111111111111
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.1111111111111111
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.08888888888888889
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.07777777777777778
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.1111111111111111
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.3333333333333333
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.4444444444444444
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.7777777777777778
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.37561164042849293
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.2550705467372134
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.26591710758377424
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.1111111111111111
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.3333333333333333
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.4444444444444444
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.7777777777777778
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.1111111111111111
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.1111111111111111
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.08888888888888889
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.07777777777777778
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.1111111111111111
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.3333333333333333
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.4444444444444444
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.7777777777777778
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.36941287151905455
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.24828042328042324
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.25912698412698415
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.1111111111111111
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.3333333333333333
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.4444444444444444
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.6666666666666666
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.1111111111111111
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.1111111111111111
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.08888888888888889
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.06666666666666668
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.1111111111111111
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.3333333333333333
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.4444444444444444
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.6666666666666666
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.33724514013077883
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.23796296296296296
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.2553057025279247
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.1111111111111111
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.3333333333333333
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.5555555555555556
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.7777777777777778
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.1111111111111111
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.1111111111111111
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1111111111111111
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.07777777777777778
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.1111111111111111
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.3333333333333333
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.5555555555555556
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.7777777777777778
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.3920021980903836
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.27248677248677244
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.2795432240996757
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.2222222222222222
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.3333333333333333
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.4444444444444444
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.5555555555555556
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.2222222222222222
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.1111111111111111
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.08888888888888889
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.05555555555555555
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.2222222222222222
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.3333333333333333
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.4444444444444444
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.5555555555555556
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.3626677657118585
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.3029100529100529
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.32598958775429365
+      name: Cosine Map@100
+---
+
+# BGE large Legal Spanish
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3). It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) <!-- at revision 5617a9f61b028005a4858fdac845db406aefb181 -->
+- **Maximum Sequence Length:** 8192 tokens
+- **Output Dimensionality:** 1024 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+- **Language:** es
+- **License:** apache-2.0
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("adriansanz/bge-m3-es-legal-tmp-6")
+# Run inference
+sentences = [
+    'Positiu, llevat els casos en els quals manquin informes preceptius i vinculants d’altres administracions o d’aquells en els què es transfereixin al sol·licitant facultats contràries al planejament i la legislació urbanística.',
+    "Quin és el sentit del silenci administratiu per a la comunicació prèvia d'obres per instal·lacions de plaques solars en sol urbà?",
+    'Quin és el lloc on es pot tramitar la presentació de justificants de pagament per als ajuts del lloguer just dels habitatges?',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+* Dataset: `dim_1024`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.1111     |
+| cosine_accuracy@3   | 0.3333     |
+| cosine_accuracy@5   | 0.4444     |
+| cosine_accuracy@10  | 0.7778     |
+| cosine_precision@1  | 0.1111     |
+| cosine_precision@3  | 0.1111     |
+| cosine_precision@5  | 0.0889     |
+| cosine_precision@10 | 0.0778     |
+| cosine_recall@1     | 0.1111     |
+| cosine_recall@3     | 0.3333     |
+| cosine_recall@5     | 0.4444     |
+| cosine_recall@10    | 0.7778     |
+| cosine_ndcg@10      | 0.3756     |
+| cosine_mrr@10       | 0.2551     |
+| **cosine_map@100**  | **0.2645** |
+
+#### Information Retrieval
+* Dataset: `dim_768`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.1111     |
+| cosine_accuracy@3   | 0.3333     |
+| cosine_accuracy@5   | 0.4444     |
+| cosine_accuracy@10  | 0.7778     |
+| cosine_precision@1  | 0.1111     |
+| cosine_precision@3  | 0.1111     |
+| cosine_precision@5  | 0.0889     |
+| cosine_precision@10 | 0.0778     |
+| cosine_recall@1     | 0.1111     |
+| cosine_recall@3     | 0.3333     |
+| cosine_recall@5     | 0.4444     |
+| cosine_recall@10    | 0.7778     |
+| cosine_ndcg@10      | 0.3756     |
+| cosine_mrr@10       | 0.2551     |
+| **cosine_map@100**  | **0.2659** |
+
+#### Information Retrieval
+* Dataset: `dim_512`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.1111     |
+| cosine_accuracy@3   | 0.3333     |
+| cosine_accuracy@5   | 0.4444     |
+| cosine_accuracy@10  | 0.7778     |
+| cosine_precision@1  | 0.1111     |
+| cosine_precision@3  | 0.1111     |
+| cosine_precision@5  | 0.0889     |
+| cosine_precision@10 | 0.0778     |
+| cosine_recall@1     | 0.1111     |
+| cosine_recall@3     | 0.3333     |
+| cosine_recall@5     | 0.4444     |
+| cosine_recall@10    | 0.7778     |
+| cosine_ndcg@10      | 0.3694     |
+| cosine_mrr@10       | 0.2483     |
+| **cosine_map@100**  | **0.2591** |
+
+#### Information Retrieval
+* Dataset: `dim_256`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.1111     |
+| cosine_accuracy@3   | 0.3333     |
+| cosine_accuracy@5   | 0.4444     |
+| cosine_accuracy@10  | 0.6667     |
+| cosine_precision@1  | 0.1111     |
+| cosine_precision@3  | 0.1111     |
+| cosine_precision@5  | 0.0889     |
+| cosine_precision@10 | 0.0667     |
+| cosine_recall@1     | 0.1111     |
+| cosine_recall@3     | 0.3333     |
+| cosine_recall@5     | 0.4444     |
+| cosine_recall@10    | 0.6667     |
+| cosine_ndcg@10      | 0.3372     |
+| cosine_mrr@10       | 0.238      |
+| **cosine_map@100**  | **0.2553** |
+
+#### Information Retrieval
+* Dataset: `dim_128`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.1111     |
+| cosine_accuracy@3   | 0.3333     |
+| cosine_accuracy@5   | 0.5556     |
+| cosine_accuracy@10  | 0.7778     |
+| cosine_precision@1  | 0.1111     |
+| cosine_precision@3  | 0.1111     |
+| cosine_precision@5  | 0.1111     |
+| cosine_precision@10 | 0.0778     |
+| cosine_recall@1     | 0.1111     |
+| cosine_recall@3     | 0.3333     |
+| cosine_recall@5     | 0.5556     |
+| cosine_recall@10    | 0.7778     |
+| cosine_ndcg@10      | 0.392      |
+| cosine_mrr@10       | 0.2725     |
+| **cosine_map@100**  | **0.2795** |
+
+#### Information Retrieval
+* Dataset: `dim_64`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value     |
+|:--------------------|:----------|
+| cosine_accuracy@1   | 0.2222    |
+| cosine_accuracy@3   | 0.3333    |
+| cosine_accuracy@5   | 0.4444    |
+| cosine_accuracy@10  | 0.5556    |
+| cosine_precision@1  | 0.2222    |
+| cosine_precision@3  | 0.1111    |
+| cosine_precision@5  | 0.0889    |
+| cosine_precision@10 | 0.0556    |
+| cosine_recall@1     | 0.2222    |
+| cosine_recall@3     | 0.3333    |
+| cosine_recall@5     | 0.4444    |
+| cosine_recall@10    | 0.5556    |
+| cosine_ndcg@10      | 0.3627    |
+| cosine_mrr@10       | 0.3029    |
+| **cosine_map@100**  | **0.326** |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 6
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `tf32`: False
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch_fused
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 16
+- `eval_accumulation_steps`: None
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 6
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: True
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: False
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch   | Step  | Training Loss | loss       | dim_1024_cosine_map@100 | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_64_cosine_map@100 | dim_768_cosine_map@100 |
+|:-------:|:-----:|:-------------:|:----------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 1.0     | 1     | -             | 3.7675     | 0.2475                  | 0.2919                 | 0.2372                 | 0.2511                 | 0.2510                | 0.2468                 |
+| **2.0** | **2** | **-**         | **3.9701** | **0.2533**              | **0.3028**             | **0.2473**             | **0.2601**             | **0.3449**            | **0.2716**             |
+| 3.0     | 4     | -             | 4.1211     | 0.2645                  | 0.2704                 | 0.2548                 | 0.2614                 | 0.3283                | 0.2654                 |
+| 4.0     | 5     | 1.8359        | 4.0228     | 0.2645                  | 0.2789                 | 0.2553                 | 0.2619                 | 0.3260                | 0.2659                 |
+| 5.0     | 6     | -             | 3.9758     | 0.2645                  | 0.2795                 | 0.2553                 | 0.2591                 | 0.3260                | 0.2659                 |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.42.3
+- PyTorch: 2.3.1+cu121
+- Accelerate: 0.32.1
+- Datasets: 2.20.0
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@misc{kusupati2024matryoshka,
+    title={Matryoshka Representation Learning}, 
+    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
+    year={2024},
+    eprint={2205.13147},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply}, 
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "BAAI/bge-m3",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.42.3",
+    "pytorch": "2.3.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d53071ba29d280f36832c2cc53e7742b4f8564bd48f1b00d02c0d80d63d13bec
+size 2271064456

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 8192,
+  "do_lower_case": false
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4f7e21bec3fb0044ca0bb2d50eb5d4d8c596273c422baef84466d2c73748b9c
+size 17083053

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}